Qwen

35B hybrid MoE (Gated DeltaNet + attention, 3B active) agent model, BF16, native 256K context on two Gaudi 2 cards.

235B MoE (22B active) instruct model, FP8 block-quantized checkpoint, 128K context on four Gaudi 2 cards.

235B MoE (22B active) reasoning model, FP8 block-quantized checkpoint, 128K context on four Gaudi 2 cards.

30B MoE (3B active) instruct model, non-thinking, served at 128K context on one Gaudi 2 card in BF16.

30B MoE (3B active) reasoning model, always thinks, served at 128K context on one Gaudi 2 card in BF16.

30B MoE (3B active) coding model with tool calling, served at 128K context on one Gaudi 2 card in BF16.

80B hybrid MoE (Gated DeltaNet + attention, 3B active) coding model with tool calling, BF16, native 256K context on four Gaudi 2 cards.

4B instruction-aware text embedding model (2560 dimensions, Matryoshka truncation) on one Gaudi 2 card in BF16.

8B instruction-aware text embedding model (4096 dimensions, Matryoshka truncation) on one Gaudi 2 card in BF16.

32B dense vision-language model (images and video) in FP8, 128K context on two Gaudi 2 cards.

8B multimodal embedding model (text, images, screenshots; 4096 dimensions, Matryoshka truncation) on one Gaudi 2 card in BF16.

122B hybrid MoE (Gated DeltaNet + attention, 10B active) reasoning model, FP8, native 256K context on four Gaudi 2 cards.

27B dense hybrid (Gated DeltaNet + attention) reasoning model with vision, FP8, native 256K context on one Gaudi 2 card.

397B MoE (17B active) hybrid (Gated DeltaNet + attention) reasoning model, FP8, native 256K context, text only, on one 8-card Gaudi 2 node.

27B dense hybrid (Gated DeltaNet + attention) reasoning model with vision, FP8, native 256K context on one Gaudi 2 card.

35B MoE (3B active) hybrid (Gated DeltaNet + attention) reasoning model with vision, FP8, native 256K context on one Gaudi 2 card.

27B dense hybrid (Gated DeltaNet + attention) reasoning model with vision, BF16, native 256K context on one Gaudi 2 card, 4 sequences.